Thinking if I can directly initialize a conv layer with custom weights in the `tf.layers` api. Maybe @fchollet or @tensorflow know that.
-
Weight values like from some pre-trained model weights saved on my disk
You can use the `set_weights` method in a TF.contrib.keras layer
-
-
Yeah, being a Keras fan I could that but sometimes things don't work out well when using `tf.contib.keras`. For example, latest issue #11867
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.